Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study.

Background: Tongue images (the colour, size and shape of the tongue and the colour, thickness and moisture content of the tongue coating), reflecting the health state of the whole body according to the theory of traditional Chinese medicine (TCM), have been widely used in China for thousands of years. Herein, we investigated the value of tongue images and the tongue coating microbiome in the diagnosis of gastric cancer (GC). Methods: From May 2020 to January 2021, we simultaneously collected tongue images and tongue coating samples from 328 patients with GC (all newly diagnosed with GC) and 304 non-gastric cancer (NGC) participants in China, and 16 S rDNA was used to characterize the microbiome of the tongue coating samples. Then, artificial intelligence (AI) deep learning models were established to evaluate the value of tongue images and the tongue coating microbiome in the diagnosis of GC. Considering that tongue imaging is more convenient and economical as a diagnostic tool, we further conducted a prospective multicentre clinical study from May 2020 to March 2022 in China and recruited 937 patients with GC and 1911 participants with NGC from 10 centres across China to further evaluate the role of tongue images in the diagnosis of GC. Moreover, we verified this approach in another independent external validation cohort that included 294 patients with GC and 521 participants with NGC from 7 centres. This study is registered at ClinicalTrials.gov, NCT01090362. Findings: For the first time, we found that both tongue images and the tongue coating microbiome can be used as tools for the diagnosis of GC, and the area under the curve (AUC) value of the tongue image-based diagnostic model was 0.89. The AUC values of the tongue coating microbiome-based model reached 0.94 using genus data and 0.95 using species data. The results of the prospective multicentre clinical study showed that the AUC values of the three tongue image-based models for GCs reached 0.88-0.92 in the internal verification and 0.83-0.88 in the independent external verification, which were significantly superior to the combination of eight blood biomarkers. Interpretation: Our results suggest that tongue images can be used as a stable method for GC diagnosis and are significantly superior to conventional blood biomarkers. The three kinds of tongue image-based AI deep learning diagnostic models that we developed can be used to adequately distinguish patients with GC from participants with NGC, even early GC and precancerous lesions, such as atrophic gastritis (AG). Funding: The National Key R&D Program of China (2021YFA0910100), Program of Zhejiang Provincial TCM Sci-tech Plan (2018ZY006), Medical Science and Technology Project of Zhejiang Province (2022KY114, WKJ-ZJ-2104), Zhejiang Provincial Research Center for Upper Gastrointestinal Tract Cancer (JBZX-202006), Natural Science Foundation of Zhejiang Province (HDMY22H160008), Science and Technology Projects of Zhejiang Province (2019C03049), National Natural Science Foundation of China (82074245, 81973634, 82204828), and Chinese Postdoctoral Science Foundation (2022M713203).

Structural and emulsifying properties of soybean protein isolate glycated with glucose based on pH treatment.

BACKGROUNDS: In the present study, a glycosylated soybean protein with glucose was prepared after pH treatment under different conditions (5.0, 6.0 7.0, 8.0, 9.0) and the conformation and emulsifying properties of soybean protein isolate (SPI) and soybean protein isolate-glucose (SPI-G) were investigated. RESULTS: The degree of grafting (37.11%) and browning (39.2%) of SPI-G conjugates were obtained at pH 9.0 (P < 0.05). The results of analysis of polyacrylamide gel electrophoresis, Fourier transform infrared spectroscopy and Endogenous fluorescence spectroscopy showed that the Maillard reaction between the SPI and glucose occurred and the natural rigid structure of test proteins was stretched and became looser, and thus the tertiary conformation was unfolding. Furthermore, the particle size of the all of samples was reduced under different pH conditions, indicating that pH treatment can increase the flexibility of SPI molecules. The proteins exhibited the best surface hydrophobicity, thermal stability and emulsifying activity (EA) of modified products when subjected to a pH treatment of 9.0, whereas they afforded the best emulsion stability (ES) at pH 8.0. There was a good correlation between the molecular flexibility and emulsifying properties of SPI-G [0.963 (F:EA) and 0.879 (F:ES)] (P < 0.05). CONCLUSION: The present study shows that the structural and emulsification characteristics of natural SPI and SPI-G conjugates have been significantly enhanced via pH treatment and these results provide a theoretical guidance for the application of glycosylated SPI in the food industry. © 2022 Society of Chemical Industry.

Effect of Ultrasonic Treatment on Freeze-thaw Stability of Soy Protein Isolate Gel.

This study investigated the impact of ultrasonic modification at various ultrasonic power extents on the freeze-thaw stability of soy protein isolate (SPI) gel. The freeze-thaw stability of the gel was evaluated by examining the changes in texture, water holding capacity, microstructure and soluble protein content during the process of 5 freeze-thaw cycles. In addition, effects on particle size, surface hydrophobicity and structure were also explored. The results showed that within a certain range, the average particle size of the protein gradually decreased, and the particle size distribution was narrower with ultrasonic intensity, it may be due to the high shear and cavitation effects of sonication that reduce the degree of protein aggregation. Furthermore, we also detected that treated proteins had lower fluorescence intensity, higher surface hydrophobicity and more flexible molecular structure with the reduction of α-helical structure as well as the rise of random coil. In terms of gel freeze-thaw stability, moderate ultrasound treatment made the water holding capacity and soluble protein content of SPI gel reduce by 38.27% and 3.58%, whereas the hardness and elasticity increased by 510.23g and 0.06mm after 5 FTC. The corresponding changes of indexes of the control group were 75.05%, 51%, 1062.75g and 0.11mm, respectively. It can be observed that the change range of treated SPI gel properties was smaller than that of natural SPI gel, indicating that ultrasonic treatment can remarkably improve the freeze-thaw stability of the gel which might have something to do with changes of protein structure.

Effect of High Pressure Treatment on Interfacial Properties, Structure and Oxidative Stability of Soy Protein Isolate-Stabilized Emulsions.

The effect of high pressure homogenization (HPH) treatment (40 to 200MPa) on the structure, interfacial properties and oxidative stability of soy protein isolate emulsions were investigated. After HPH process, emulsifying activity (EAI) and emulsion stability (ESI) could be improved by 114% and 125%, percentage of protein adsorbed to oil-in-water emulsions significantly improved when the pressure was not more than 160 MPa. SDS-PAGE showed that the HPH caused more low molecular mass subunits as the samples were treated below 160 MPa. FTIR traced the changes of four conformations in the secondary structure. Within a suitable pressure range, the apparent viscosity increased with the increasing of pressure, which reflected shear thinning; rheological measurement of emulsions showed G'>G'', G' and G'' both increased significantly with frequency increasing; emulsions treated by HPH had better oxidative stability. This paper suggested the HPH was a useful method for preparation the highly viscous and stable emulsions.